Development and Application of Natural Language Processing on Unstructured Data in Hypertension: A Scoping Review

BackgroundHypertension is a global health concern with a vast body of unstructured data, such as clinical notes, diagnosis reports, and discharge summaries, that can provide valuable insights. Natural Language Processing (NLP) has emerged as a powerful tool for extracting knowledge from unstructured data. This scoping review aims to explore the development and application of NLP on unstructured clinical data in hypertension, synthesizing existing research to identify trends, gaps, and underexplored areas for future investigation. MethodsWe conducted a systematic search of electronic databases, including PubMed/MEDLINE, Embase, Cochrane Library, Scopus, Web of Science, ACM Digital Library, and IEEE Xplore Digital Library, to identify relevant studies published until the end of 2022. The search strategy included keywords related to hypertension, NLP, and unstructured data. Data extraction included study characteristics, NLP methods, types of unstructured data sources, and key findings and limitations. ResultsThe initial search yielded 951 articles, of which 45 met the inclusion criteria. The selected studies spanned various aspects of hypertension, including diagnosis, treatment, epidemiology, and clinical decision support. NLP was primarily used for extracting clinical information from unstructured electronic health records (EHRs) documents and text classification. Clinical notes were the most common sources of unstructured data. Key findings included improved diagnostic accuracy and the ability to comprehensively identify hypertensive patients with a combination of structured and unstructured data. However, the review revealed a lack of more advanced NLP techniques used in hypertension, generalization of NLP outside of benchmark datasets, and a limited focus on the integration of NLP tools into clinical practice. DiscussionThis scoping review highlights the diverse applications of NLP in hypertension research, emphasizing its potential to transform the field by harnessing valuable insights from unstructured data sources. There is a need to adopt and customize more advanced NLP for hypertension research. Future research should prioritize the development of NLP tools that can be seamlessly integrated into clinical settings to enhance hypertension management. ConclusionNLP demonstrates considerable promise in gleaning meaningful insights from the vast expanse of unstructured data within the field of hypertension, shedding light on diagnosis, treatment, and the identification of patient cohorts. As the field advances, there is a critical need to promote the use and development of advanced NLP methodologies that are tailored to hypertension and validated on real-world unstructured data.